Debian Patches

Status for rocblas/6.4.3+dfsg-1~exp1

Patch Description Author Forwarded Bugs Origin Last update
use-generic-blas-for-reference.patch use generic blas for reference
The upstream project typically uses either the AOCL BLIS library or the
Netlib BLAS library as the reference implementation in the test suite on
Linux. However, the OpenBLAS library is used by upstream on Windows. It
would be nice to use OpenBLAS on Debian for performance reasons (as the
test suite is heavily CPU-bound), however, the Netlib implementation
seems to be more reliable for achieving a full suite of passing tests.		 Cordell Bloor <cgmb@slerp.xyz> not-needed 2025-07-04
remove-use-of-pip-and-virtualenv.patch remove use of pip and virtualenv
The upstream project creates a virtualenv and uses pip to install the
Python dependencies during a build. In the Debian build, all the Python
dependencies are already provided by packages, so there's no need for
all that complexity.

When contributed upstream, this functionality was guarded behind the
cmake option -DBUILD_WITH_PIP=OFF. Tensile_ROOT can also be passed from
d/rules (if necessary) so this patch can be dropped with ROCm 5.7.		 Cordell Bloor <cgmb@slerp.xyz> invalid 2023-04-09
mark-known-bugs.patch mark known bugs
In ROCm 5.5, the FP16 High-Precision Accumulate checks are also offset
from the correct answer by margins slightly greater than those allowed.		 Cordell Bloor <cgmb@slerp.xyz> not-needed 2023-07-16
make-openmp-optional.patch make openmp optional Cordell Bloor <cgmb@slerp.xyz> no 2023-04-09
move-tensile-library-into-versioned-subdir.patch move tensile library into versioned subdir
The Tensile library contains optimized kernels that are loaded at
runtime by rocblas, and thus must be a part of the library package.
To ensure that multiple versions of rocblas with different ABI
versions can be installed side-by-side, the library files must be
moved to a path containing the version number.		 Cordell Bloor <cgmb@slerp.xyz> invalid 2025-07-04
remove-references-to-dfsg-violating-kernels.patch remove references to dfsg-violating kernels
The DGEMM_Aldebaran_PKFixedAtomic512Latest and
DGEMM_Aldebaran_PKFixedAtomic512_104 kernels were removed for dfsg
reasons, and references to those kernels must be removed to fix the
build. This will result in a performance drop on MI200 GPUs because
the tuned assembly kernels will be replaced with fallback
implementations for these problems.

This problem has been reported upstream and they intend to supply a
better fix.		 Cordell Bloor <cgmb@slerp.xyz> not-needed 2025-07-04
expand-isa-compatibility.patch expand isa compatibility
This is not an ideal solution, but there are a number of ISAs that are
subsets of gfx900, gfx1010 and gfx1030. The simplest way to get
rocBLAS and Tensile to load the compatible kernels when running on
architectures compatible with those ISAs is to simply report the
GPU as being of the supported type.

There is no way this patch would be accepted upstream as it is expected
that they will implement a better solution... eventually.

Updated by @ckk to support HIP >= 6.		 Cordell Bloor <cgmb@slerp.xyz> not-needed 2025-07-06
Enable-changing-directory-for-test-data.patch Enable changing directory for test data
On Debian, we install to a versioned directory based on the library
name.		 Christian Kastner <ckk@debian.org> not-needed 2025-07-07
print-kernel-name-for-missing-attribute-error.patch print kernel name for missing attribute error
It is difficult to debug a failed build without knowing what kernel
caused the issue. In theory, this error should never occur. However,
the logging will be useful if it does.		 Cordell Bloor <cgmb@slerp.xyz> not-needed 2025-07-04
verbose-tensile-source-kernel-build.patch verbose tensile source kernel build
The build of the Tensile source kernels takes quite a long time, so it
may time out on slower machines if there is no output in too long. The
verbose flag should add some output at the start of the build for each
offload architecture, which should help prevent timeout.		 Cordell Bloor <cgmb@slerp.xyz> not-needed 2025-07-04
Skip-git-requirement.patch Skip git requirement
It appears to be used only for the git commit ID, which we can work
around.		 Christian Kastner <ckk@debian.org> not-needed 2025-07-04
Use-local-mathjax.patch Use local mathjax
The sphinx.ext.mathjax extension defaults to loading mathjax from a
CDN, which results in the lintian warning 'privacy-breach-generic'.
Use a local copy of mathjax to prevent that problem.		 Cordell Bloor <cgmb@slerp.xyz> not-needed 2023-12-21
Extend-docs-conf.py-for-offline-build.patch Extend docs/conf.py for offline build
By setting these extra variables, we can suppress a remote call which
would cause the build to fail.		 Christian Kastner <ckk@debian.org> no 2025-07-04

All known versions for source package 'rocblas'

Links